{"total":117,"rows":[{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174,"area":"driving"},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109,"area":null},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90,"area":null},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85,"area":"diffusion"},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77,"area":"diffusion"},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50,"area":null},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46,"area":null},{"id":"2307.01849","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","created":"2023-07-04","cited_by_count":40,"area":"diffusion"},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36,"area":null},{"id":"2108.12099","title":"Learning to Give Checkable Answers with Prover-Verifier Games","created":"2021-08-27","cited_by_count":32,"area":null},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31,"area":null},{"id":"2202.07135","title":"Compositional Scene Representation Learning via Reconstruction: A Survey","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2102.10303","title":"Towards Building A Group-based Unsupervised Representation Disentanglement Framework","created":"2021-02-20","cited_by_count":22,"area":null},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20,"area":"lr"},{"id":"2306.06997","title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","created":"2023-06-12","cited_by_count":20,"area":null},{"id":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20,"area":null},{"id":"2303.02260","title":"Learning to reason over visual objects","created":"2023-03-03","cited_by_count":19,"area":"lr"},{"id":"2106.02923","title":"Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization","created":"2021-06-05","cited_by_count":17,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2305.15001","title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2306.08068","title":"DORSal: Diffusion for Object-centric Representations of Scenes et al","created":"2023-06-13","cited_by_count":16,"area":"diffusion"},{"id":"2503.06170","title":"Object-Centric World Model for Language-Guided Manipulation","created":"2025-03-08","cited_by_count":16,"area":"wm"},{"id":"2106.05886","title":"Group Equivariant Subsampling","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2409.13475","title":"PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2310.12690","title":"Neurosymbolic Grounding for Compositional World Models","created":"2023-10-19","cited_by_count":14,"area":"wm"},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2107.08881","title":"Reasoning-Modulated Representations","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2501.15878","title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","created":"2025-01-27","cited_by_count":13,"area":"diffusion"},{"id":"2204.02283","title":"Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2311.04640","title":"Object-Centric Learning with Slot Mixture Module","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2403.03458","title":"Slot Abstractors: Toward Scalable Abstract Visual Reasoning","created":"2024-03-06","cited_by_count":11,"area":"lr"},{"id":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11,"area":null},{"id":"2505.20772","title":"MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2103.12045","title":"Raven's Progressive Matrices Completion with Latent Gaussian Process Priors","created":"2021-03-22","cited_by_count":9,"area":null},{"id":"2203.11194","title":"Test-time Adaptation with Slot-Centric Models","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9,"area":"lr"},{"id":"2406.07141","title":"Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"1907.13627","title":"Disentangled Relational Representations for Explaining and Learning from Demonstration","created":"2019-07-31","cited_by_count":8,"area":"offlinerl"},{"id":"2006.09107","title":"Learning from Demonstration with Weakly Supervised Disentanglement","created":"2020-06-16","cited_by_count":8,"area":"offlinerl"},{"id":"2305.18890","title":"Sensitivity of Slot-Based Object-Centric Models to their Number of Slots","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2305.19550","title":"Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior","created":"2023-05-31","cited_by_count":8,"area":null},{"id":"2210.05519","title":"Robust and Controllable Object-Centric Learning through Energy-based Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","cited_by_count":7,"area":null},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2111.05986","title":"SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2305.05591","title":"AudioSlots: A slot-centric generative model for audio separation","created":"2023-05-09","cited_by_count":5,"area":null},{"id":"2410.15728","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2312.04947","title":"Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images","created":"2023-12-08","cited_by_count":4,"area":null},{"id":"2401.10148","title":"Explicitly Disentangled Representations in Object-Centric Learning","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2501.12477","title":"Slot-BERT: Self-supervised Object Discovery in Surgical Video","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2511.14262","title":"Object-Centric World Models for Causality-Aware Reinforcement Learning","created":"2025-11-18","cited_by_count":4,"area":"wm"},{"id":"2605.14937","title":"Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations","created":"2026-05-14","cited_by_count":4,"area":"wm"},{"id":"2308.10441","title":"X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2404.19654","title":"Masked Multi-Query Slot Attention for Unsupervised Object Discovery","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2509.16447","title":"Local Mechanisms of Compositional Generalization in Conditional Diffusion","created":"2025-09-19","cited_by_count":3,"area":"diffusion"},{"id":"2601.01224","title":"Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment","created":"2026-01-03","cited_by_count":3,"area":"diffusion"},{"id":"2104.14386","title":"Pre-training of Deep RL Agents for Improved Learning under Domain Randomization","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2207.07512","title":"Sparse Relational Reasoning with Object-Centric Representations","created":"2022-07-15","cited_by_count":2,"area":null},{"id":"2310.08929","title":"Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2311.07534","title":"Unsupervised Musical Object Discovery from Audio","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2402.02217","title":"CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse","created":"2024-02-03","cited_by_count":2,"area":null},{"id":"2407.04170","title":"Attention Normalization Impacts Cardinality Generalization in Slot Attention","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2409.13846","title":"Multi-Modality Conditioned Variational U-Net for Field-of-View Extension in Brain Diffusion MRI","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2506.03798","title":"CoLa: Chinese Character Decomposition with Compositional Latent Components","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.01882","title":"Future Slot Prediction for Unsupervised Object Discovery in Surgical Video","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2606.23436","title":"Rethinking Object-Centric Representations for Video Dynamics Modeling","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2110.03628","title":"Boxhead: A Dataset for Learning Hierarchical Representations","created":"2021-10-07","cited_by_count":1,"area":null},{"id":"2206.01370","title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2210.11394","title":"Solving Reasoning Tasks with a Slot Transformer","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2210.14139","title":"Learning Explicit Object-Centric Representations with Vision Transformers","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2304.01430","title":"Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2304.04103","title":"TC-VAE: Uncovering Out-of-Distribution Data Generative Factors","created":"2023-04-08","cited_by_count":1,"area":null},{"id":"2306.12955","title":"Triggering Dark Showers with Conditional Dual Auto-Encoders","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2307.07147","title":"Linking vision and motion for self-supervised object-centric perception","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2307.14151","title":"Learning Disentangled Discrete Representations","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2402.12675","title":"Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach","created":"2024-02-20","cited_by_count":1,"area":"lr"},{"id":"2406.18220","title":"Guiding Video Prediction with Explicit Procedural Knowledge","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2407.03216","title":"Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2409.18017","title":"Transferring disentangled representations: bridging the gap between synthetic and real images","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2410.00728","title":"Simplified priors for Object-Centric Learning","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2502.11655","title":"TextOCVP: Object-Centric Video Prediction with Language Guidance","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2505.02071","title":"Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2505.19110","title":"An Interpretable Representation Learning Approach for Diffusion Tensor Imaging","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2510.21402","title":"Disentangled Representation Learning via Modular Compositional Bias","created":"2025-10-24","cited_by_count":1,"area":null}],"next_cursor":"100"}